88 results about "Linear programming algorithm" patented technology

The invention relates to the technical field of steel production plan optimization based on multi-dimensional constraint dynamic coupling, in particular to a molten iron operation plan arrangement method based on dynamic constraint modeling hybrid optimization, which comprises the following steps: acquiring order data, equipment state data and constraint rule data to generate structured input parameters comprising order priority labels; constructing a multi-objective optimization model based on the molten iron distribution constraint and the maintainable time length of the equipment, extracting the maintenance conflict relationship between the equipment groups, constructing a maintenance rule knowledge graph, and generating a dynamic constraint condition set; generating an initial molten iron distribution and maintenance plan through global search by adopting a genetic algorithm, and outputting a molten iron distribution path and an equipment maintenance time sequence through local optimization by combining a linear programming algorithm; according to the method, dynamic collaborative optimization of molten iron distribution and equipment maintenance is achieved, and the resource utilization rate, the order delivery rate and the production system stability are improved.

The invention discloses a complex geological weak surrounding rock tunnel micro-disturbance green blasting construction method which comprises the following steps: acquiring multi-source data through a sensor and geological survey equipment, and extracting a standardized feature set; and constructing a blasting parameter and surrounding rock response prediction model by using a random forest algorithm, inputting explosive load and hole net parameters, and outputting predicted surrounding rock deformation and vibration values. And if the vibration value exceeds the environment-friendly threshold value, adjusting the parameter by adopting a gradient descent algorithm until the requirement is met. And in combination with real-time monitoring data, the surrounding rock response is dynamically updated by using a Kalman filtering algorithm. If the overexcavation probability exceeds the threshold value, the parameters are further optimized through a genetic algorithm. And finally, optimizing resource allocation through a linear programming algorithm, and determining a final blasting scheme. Intelligent regulation and control of blasting parameters of the weak surrounding rock tunnel are achieved, vibration and deformation are effectively controlled, the overexcavation risk is reduced, the construction efficiency and quality are improved, and a new technical scheme is provided for similar projects.

The invention discloses a rice field irrigation control method, and belongs to the field of rice field irrigation, and the method comprises the steps: obtaining soil humidity, water level and meteorological data from a rice field through a sensor network, storing the data in a pre-established distributed database, and obtaining a multi-source data set; according to the data set in the unified format, key features of soil humidity, water level and meteorological data are extracted by adopting a principal component analysis method, and a feature vector set is obtained; if the water consumption of the predicted irrigation scheme exceeds a preset threshold value, the scheme is optimized and adjusted through a linear programming algorithm, and an optimized irrigation scheme is obtained; according to the optimized irrigation scheme, the water consumption in the irrigation process is monitored in real time through flow meter equipment, and accurate measurement data are obtained; and the accurate measurement data is distributed through a quota management module, a regional water resource allocation scheme is generated by adopting a dynamic quota algorithm, and a quota management result is obtained.

The invention discloses a building energy system multi-type demand response operation strategy optimization method and system, and relates to the technical field of building energy management and demand response optimization control, and the method comprises the steps: collecting building user side multi-source information, building a building cooling load prediction structure, and bringing the structure into an optimization scheduling model input system. Constructing a building energy system optimization scheduling equipment model; collecting power grid side information, and dynamically loading an optimal scheduling model for a time-of-use electricity price scene and a peak clipping scene based on judgment of power grid demand response type information of the next day; analyzing an optimization problem of a unified objective function in a double-type response scene, introducing a power reservation coefficient based on a time-of-use electricity price scene, and controlling flexible resource retention; a mixed integer linear programming algorithm is adopted to solve the multi-scene optimization scheduling model, and a corresponding strategy, scheme and power configuration plan are generated; according to the method, flexible dynamic regulation and control and unified scheduling in a multi-response scene are realized, and the strategy adaptability and collaboration are improved.

The invention discloses a power distribution network reconstruction method and device based on the Stackelberg game, and belongs to the technical field of electric power systems, and the reconstruction method comprises the steps: modeling the attack and defense confrontation of an attacker and a defender as the Stackelberg game, taking the attacker as a leader, the defender as a follower, and taking network reconstruction as a defense means; a blog framework is provided for formulating an optimal defense means; and fusing the game framework and a mixed integer linear programming algorithm, and calculating an optimal defense means of the defender by solving a Stackelberg equilibrium point. According to the method, the optimal defense scheme for coping with a strategic attacker can be calculated, and the uncertainty of attack positioning is considered in decision making, so that the minimum system reconstruction cost is realized while the voltage safety of the power grid is ensured, and the safety and the toughness of the power distribution network under network attacks are effectively improved.

A regional building cooling and heating load artificial neural network energy distribution optimization method disclosed by the present invention comprises the steps of obtaining inter-regional topological relation data and load-related data, constructing a graph network model to capture spatial dependency, fusing meteorological data and historical load records to generate a multivariable dynamic data set, and obtaining the optimal energy distribution of the cooling and heating load artificial neural network. Processing the multivariable dynamic data set by adopting a graph convolutional neural network to obtain an initial prediction result, adjusting the initial prediction result through an artificial neural network to generate adjusted load distribution data, and analyzing by combining a heat transfer rule and a time sequence to obtain spatial and temporal distribution characteristics; and integrating equipment efficiency constraint and cost fluctuation data by adopting a multi-objective optimization algorithm to obtain an optimized objective function value, adjusting equipment dynamic parameters through deep reinforcement learning to obtain a parameter adjustment scheme, and optimizing an energy distribution proportion by adopting a linear programming algorithm to obtain a final energy distribution scheme.

The invention discloses an improvement method of a large language model, electronic equipment and a storage medium, and the method comprises the steps: calculating a correlation matrix between middle layers through a public data set, and calculating mutual information redundancy between the layers based on the correlation matrix between the middle layers, an inter-layer redundancy matrix is constructed through mutual information redundancy among the layers; calculating the total redundancy of each layer based on the redundancy matrix, and generating a layer importance factor through function conversion; establishing an objective function based on the layer importance factors and constructing a linear optimization model of sparse rate distribution of each layer; solving the optimization model by adopting a linear programming algorithm to obtain an optimal sparse rate distribution scheme of each layer; differentiated pruning is carried out on each layer of weight matrix according to the distribution scheme, a weight parameter with the maximum amplitude in each layer of weight matrix is reserved, the rest parameters are set to be zero, and a sparse weight matrix is obtained; according to the method, the features can be selectively pruned in the middle layer, so that fine-grained optimization of a large language model is realized.

The invention discloses a mixed integer linear programming-based iron and steel industry power grid interactive full-process scheduling method. The method comprises the specific steps of S1, constructing a dynamic balance equation and an energy storage equipment dynamic management model; s2, establishing a multi-energy coupling collaborative optimization model; s3, setting a target function, an energy storage equipment constraint condition and a key equipment power constraint condition; s4, embedding a demand response load adjustment model; and S5, based on the model embedded in the step S4, solving by using a mixed integer linear programming algorithm to obtain an optimal scheduling scheme. According to the iron and steel industry power grid interactive full-process scheduling method based on mixed integer linear programming, by constructing an iron making-steel making-rolling full-process energy flow dynamic coupling model, secondary energy balance of coal gas, steam and the like and power grid demand response instructions are integrated, and collaborative optimization of energy and production between processes is achieved.

The invention discloses a synergistic proportioning method for multiple scrap aluminum capable of reducing the proportion of pure aluminum ingots, and relates to the technical field of aluminum smelting and secondary aluminum, the method comprises the following steps: S1, collecting and sorting scrap aluminum: collecting any three scrap aluminum from door and window scrap aluminum, automobile scrap aluminum, zip-top can scrap aluminum and industrial leftover scrap aluminum, collecting, and removing impurities in the scrap aluminum; s2, component detection: respectively detecting the aluminum content and impurity elements of each scrap aluminum in the step S1 by using a direct-reading spectrometer; according to the method, the proportion is automatically calculated through a linear programming algorithm, traditional empirical proportion is replaced, the proportion calculation time is shortened, and the batching efficiency is greatly improved. Meanwhile, the qualified rate of finished product detection is improved, the number of reworking times is reduced, the production cycle is shortened, the production efficiency and market response capability of enterprises are improved, and the enterprises are helped to quickly meet customer order requirements.

The invention discloses a production resource scheduling method for a container bottom plate, and relates to the technical field of container manufacturing, and the method comprises the steps: S1, collecting heat conductivity coefficient data and local temperature gradient distribution data in a bottom plate machining process through a sensor array, processing the data through a Fourier transform method, and extracting low-frequency domain features; the space-time non-uniform change trend of the heat conductivity coefficient is obtained; s2, according to the space-time non-uniform change trend, judging whether the current processing state deviates from a preset heat-conducting property threshold value or not, if the current processing state deviates from the preset heat-conducting property threshold value, starting a linear programming algorithm through constraint condition setting and objective function definition, optimizing a material adding proportion and temperature control parameters, and determining an adjusted parameter combination; according to the production resource scheduling method for the container bottom plate, the stability of the heat conduction performance is remarkably improved, resource consumption is reduced, and efficient and accurate control over micro-scale machining is achieved.

The invention discloses a multi-energy system optimization method and system based on hydrogen energy storage, and belongs to the field of multi-energy system optimization, and the method comprises the steps: obtaining the historical wind speed, wind direction and solar irradiance data of an anemometer tower and a photovoltaic power station, training a time sequence analysis model through the historical wind speed, wind direction and solar irradiance data, and obtaining a time sequence analysis model; wind energy power and solar energy power prediction curves in a future time period are obtained; the method comprises the following steps: acquiring pressure and temperature data of a hydrogen storage tank, inputting the pressure and temperature data into a pre-established leakage rate dynamic compensation algorithm to obtain a real-time hydrogen loss amount, and if the hydrogen loss amount is greater than a preset threshold value, reducing the operation pressure or temperature of the hydrogen storage tank; and according to the wind and light power prediction curve, the hydrogen production equipment operation data, the hydrogen storage tank operation parameters, the hydrogen conversion equipment control signal, the constraint model and the income cost model as input of a linear programming algorithm, an equipment capacity configuration scheme for maximizing the system economic benefits is obtained.

The invention belongs to the technical field of flexible resource scheduling management, discloses a virtual power plant multi-element flexible resource day-to-day rolling optimization scheduling method, system and device considering random deviation and a medium, and aims to solve the problems of poor collaboration among resources and high quantity-price cost of resource regulation and control. The method comprises the steps of obtaining resource configuration parameter information, a scheduling plan preset for flexible resources and response day operation boundary information corresponding to the scheduling plan; respectively establishing control models and setting constraint conditions for various flexible resources; obtaining a quantity-price curve and an adjustable interval of the flexible resource, and based on the quantity-price curve and the adjustable interval, constructing a target function with minimum power tracking cost and minimum power tracking deviation in response to the scheduling plan as targets; based on the objective function, solving each control model by adopting a mixed integer linear programming algorithm to obtain a corresponding power deviation correction value, and scheduling each flexible resource based on the power deviation correction value; and re-executing the steps at the next moment based on the scheduled operation result at the current moment.

The invention relates to an intelligent road maintenance closed-loop decision-making system based on budget constraint and fund matching, and belongs to the technical field of road operation and maintenance. The data fusion and recognition layer is used for performing feature extraction, fusion and disease recognition on the multi-source data and outputting standardized disease entries; the decision optimization layer is used for solving an optimal repair strategy by adopting a mixed integer linear programming algorithm based on disease items, material inventory information, budget constraints, construction resources, traffic flow prediction and weather data; the fund matching and work order generation layer is used for outputting financing labels and electronic work orders according to an evaluation and rule engine; and the acceptance and backtracking layer is used for collecting a detection result after construction is completed, calculating a repair quality coefficient and feeding back the repair quality coefficient to the model for updating. According to the invention, full-automatic closed-loop management is realized, the whole process from disease identification to work order issuing to acceptance feedback is free of human intervention, the fund use efficiency is improved, and the repair quality and transparency are improved.

The invention discloses an intelligent observation station planning method based on a ground laser scanner in a complex forest area environment, and the method comprises the following steps: S1, employing a spatial analysis method based on multi-source geometric constraints, and achieving the separation of a single tree hierarchical structure; s2, evaluating the visual range of the candidate points according to occlusion judgment; s3, performing visibility analysis to select efficient candidate points; and S4, selecting a final frame site based on fusion of heuristic search and integer linear programming. According to the intelligent observation station planning method based on the ground laser scanner in the complex forest area environment, firstly, efficient candidate point identification is carried out by adopting multi-source geometric constraint, single tree and candidate point distribution condition identification, shielding judgment and visibility analysis, and then heuristic search and an integer linear programming algorithm are fused; and the final position of the ground laser scanner stand is obtained. Compared with a traditional algorithm, the optimization algorithm based on the visibility constraint can greatly reduce the number of stand stations and improve the calculation efficiency under the condition that the scanning integrity is guaranteed.

This invention discloses a joint clearing method and system for the electricity spot market that considers the generalized energy storage characteristics of electric vehicle aggregators. Based on the operational characteristics and physical constraints of large-scale electric vehicle access to the electricity spot market, and combined with the theory of generalized energy storage efficiency, an embedded constraint model is constructed, including charging and discharging power boundaries, energy state temporal coupling, and terminal electricity demand. This enables quantitative modeling and unified scheduling of the flexibility resources of electric vehicle aggregators. Data cleaning and parameter normalization methods are used to map the characteristics of dispersed electric vehicle clusters to standardized virtual power plant parameters. State equation constraints are introduced into the traditional DC optimal power flow and unit combination model. Combining mixed-integer linear programming algorithms and dual pricing theory, the optimal coordination strategy between conventional unit output and electric vehicle charging and discharging is solved, and the low-cost clearing and nodal marginal price of the spot market are calculated. The method of this invention can improve the level of renewable energy consumption and the economy and security of grid operation.

The invention relates to the technical field of terminal data acquisition, and particularly discloses a terminal data acquisition system and method based on 5G edge collaboration and a storage medium, the system comprises a data acquisition module, a type judgment module, a transfer cost confirmation module and a dynamic transfer module; according to the method, the historical garbage throwing data, the traffic flow and the pedestrian flow of the garbage throwing points are comprehensively analyzed, the required throwing number of the garbage cans can be accurately analyzed, then the throwing points to be added and the excessive throwing points are accurately screened out, and the requirement trend index is calculated through the secondary accumulation and the primary exponential smoothing method; a demand putting coefficient is determined through a linear regression algorithm in combination with a circulation value, the actual demand of a garbage putting point can be more scientifically reflected, finally, dynamic transferring is performed under the condition that the garbage can number constraint condition is met by adopting a linear programming algorithm and taking the minimum total transferring cost as a target function, and scientific allocation of the garbage can putting number is achieved.

The application provides an artificial intelligence-based supplier food ERP whole-chain inventory early warning system, relates to the technical field of food inventory monitoring, and comprises a data acquisition and processing module, an inventory prediction module, an inventory early warning module and an ERP execution module; the data acquisition and processing module is used for acquiring whole-chain inventory data and pre-processing the whole-chain inventory data; the inventory prediction module is used for predicting future inventory; the inventory early warning module is used for presetting inventory early warning rules and early warning future inventory; and the ERP execution module is used for generating a restocking strategy. The application accurately predicts future inventory changes by means of a time series model, a machine learning model and a fusion strategy, so that an enterprise can plan production and procurement in advance; potential inventory risks are discovered in time by means of multi-dimensional early warning rules and a risk assessment matrix, so as to reduce out-of-stock or overstock losses; and the ERP execution module generates an optimal restocking strategy based on a cost model and a linear programming algorithm, and the restocking strategy is dynamically adjusted in combination with a real-time state of a supply chain, so as to reduce the costs of procurement, transportation and warehousing while ensuring supply.

The invention provides a fair clustering method and device for large-scale data, equipment and a medium, and the method comprises the steps: constructing a to-be-classified data set after carrying out the normalization processing of the obtained to-be-clustered large-scale data, solving the to-be-classified data set through a greedy algorithm, obtaining an initial solution, and carrying out the clustering of the to-be-clustered large-scale data. And then sampling the data set, combining the sampled data set with the initial solution to form a weighted instance of the original data, executing a linear programming algorithm to obtain an intermediate solution, and iterating the intermediate solution through a local search algorithm meeting a fair condition to obtain a local optimal solution. The solution of the constant approximation ratio can be obtained within the time complexity in linear relation with the data scale, that is, the algorithm operation time is in direct proportion relation with the data scale, and compared with a traditional method, the solution efficiency and the solution quality are remarkably improved.

The invention discloses a ship energy optimization method considering energy storage life and flexible navigation. The ship energy optimization method comprises the following steps: step 1, constructing a ship flexible navigation model based on marine environment data and an electronic chart system; establishing an energy storage attenuation model of the battery energy storage system, wherein the model comprises quantitative calculation and linear processing of calendar life attenuation and cycle life attenuation; constructing a photovoltaic output model dynamically associated with the ship position, wherein the model comprises solar irradiation calculation, photovoltaic panel efficiency correction and environmental factor influence evaluation; 2, a flexible navigation model, an energy storage attenuation model and a photovoltaic output model are integrated, an SIES multi-objective optimization model is established, and the model aims at minimizing the total cost of the system; and 3, solving the SIES multi-objective optimization model by adopting a mixed integer linear programming algorithm to obtain an optimal route planning, energy storage configuration and energy scheduling scheme.

The application relates to the technical field of cloud computing and servers, and particularly discloses a computing power and power collaborative scheduling optimization method and system based on multiple levels of requirements, wherein the method comprises the following steps: determining a computing power supply-demand gap according to a computing power demand curve and a renewable energy power generation curve; determining a cost function of each period under each scene according to the computing power supply-demand gap, establishing a computing power scheduling model, a power scheduling model and a power scheduling optimization model based on a storage energy source; dividing the cost into a cost saving part and an energy saving and emission reduction part according to the cost function of each period under each scene; and minimizing the cost of the cost saving part and maximizing the income of the energy saving and emission reduction part through an iterative linear programming algorithm, so as to obtain a computing power allocation result of each period; and according to the computing power allocation result, the computing power supply-demand gap is gradually reduced through iteration until the supply-demand gap is smaller than a predetermined threshold, so that a final computing power and power collaborative scheduling scheme is obtained.

This invention discloses a method, system, and equipment for disaster relief using swarm robots. The method includes: simulating a disaster relief scenario; determining the hard rules that each robot in the swarm must follow based on its actions and states in the simulated scenario; constructing a functional relationship between the adoption rate of social rules and the performance indicators of the swarm robots; constructing a compromise decision model based on the performance indicators, the social rules, and the functional relationship; solving the compromise decision model using an adaptive linear programming algorithm and performing multi-objective visual trade-off analysis to obtain the range of social rule adoption rates that satisfies all the performance indicators; and directing the swarm robots to perform disaster relief based on the range of social rule adoption rates. This invention can minimize casualties and property damage in disaster relief.

The present disclosure belongs to the technical field of power system distribution network planning, and particularly relates to an active distribution network planning method and system, comprising the following steps: obtaining basic data of an active distribution network; constructing an active distribution network planning model with a minimum annual comprehensive cost as an objective function, considering renewable energy reserve uncertainty and electric vehicle reserve delay, according to the obtained data; linearizing the nonlinear active distribution network planning model, and solving the linearized active distribution network planning model by using a mixed integer linear programming algorithm to obtain a planning scheme of the active distribution network.

The invention provides a supplier food ERP full-chain inventory early warning system based on artificial intelligence, and relates to the technical field of food inventory monitoring, and the system comprises a data collection and processing module which is used for collecting full-chain inventory data, and carrying out the preprocessing of the full-chain inventory data; the inventory prediction module is used for predicting future inventory; the inventory early warning module is used for presetting inventory early warning rules and performing early warning on future inventory; and the ERP execution module is used for generating a replenishment strategy. By means of the time sequence model, the machine learning model and the fusion strategy, future inventory changes are accurately predicted, and enterprises can plan production and purchase in advance; through a multi-dimensional early warning rule and a risk assessment matrix, potential inventory risks are found in time, and stockout or overstock loss is reduced; an optimal replenishment strategy is generated based on a cost model and a linear programming algorithm through an ERP execution module, and the real-time state dynamic adjustment of a supply chain is combined, so that the cost of purchase, transportation, storage and the like is reduced while the supply is ensured.

The application discloses a building integrated energy system operation strategy and declaration capacity optimization method considering demand response effectiveness requirements. First, the basic information of the building user side and the power grid side is collected; second, a building integrated energy system optimization scheduling model is established; then, an optimization solving problem of the building integrated energy system optimization scheduling model considering the demand response effectiveness requirements is determined; finally, a mixed integer linear programming algorithm is used to solve the optimization solving problem of the building integrated energy system optimization scheduling model, and the optimal declaration capacity value scheme and the operation strategy scheme are obtained. By using the application, the requirements of the power grid on the user information declaration can be met when the building user participates in the invitation type demand response, the declaration capacity value recommendation scheme and the response strategy recommendation scheme are provided for the user; and based on the response effectiveness auditing mechanism formulated by the power grid, the actual response effect of the user is improved, and the target of further reducing the operation cost of the user is achieved.

The invention provides an industrial coal blending optimization method and system based on multi-agent collaboration and a program product, and relates to the technical field of industrial intelligent control and data processing. The method comprises the following steps: acquiring production state data of a current time step, wherein the data contains coal inventory, physicochemical indexes and raw material resource weight coefficients; inputting the data into a mechanism calculation module, and calculating a reference ratio vector by using a linear programming algorithm with the purpose of minimizing a comprehensive resource consumption index; meanwhile, inputting the data into a strategy correction agent, and outputting a correction action vector aiming at a reference ratio and a confidence factor of a current working condition; and carrying out dynamic weighted fusion on the reference ratio and the correction action. A double-layer coupling framework of mechanism guarantee and AI efficiency improvement is adopted, a confidence factor is used as a safety valve, on the premise that production safety is guaranteed, the problems that a traditional coal blending model is poor in non-linear adaptive capacity, lagged in feedback and the like are solved, and global optimization of industrial raw material configuration is achieved.

The invention discloses a metering method, device and system for setting production by sales, and solves the problems of warehouse expansion and production halt caused by full-load production of surface mines. The method comprises the following steps: firstly, collecting and calibrating data such as inventory, sales volume and productivity; then, based on the inventory available capacity and the sales volume predicted through a quadratic polynomial regression model, combining productivity constraints, and taking a minimum value to determine the maximum production plan quantity of single-specification finished products; under the constraint of the finished product proportion, optimizing the production capacity proportion of each specification by using a linear programming algorithm, and calculating the total planned quantity and the production duration; and finally, issuing a production instruction and performing real-time monitoring, and when the inventory is close to the upper limit or the sales volume suddenly exceeds the threshold value, re-triggering the plan calculation process to form a closed loop of data acquisition, calculation, execution and feedback. The scheme can dynamically match the sales volume and the productivity, avoids warehouse expansion, improves the resource utilization rate, reduces the production cost, and is suitable for production scenes of multi-specification finished products.

This invention provides a linear programming method and system for scheduling cleaning operations under multiple constraints. It collects multi-dimensional constraint feature values ​​and basic operational data from cleaning operation scenarios, constructs a linear programming mathematical model integrating multiple constraints, and sets an objective function and a set of constraint equations. A linear programming algorithm is used to optimize the model to obtain an initial scheduling scheme. Based on dynamic adjustment rules for cleaning operations, the initial scheduling scheme is iteratively optimized to generate an optimal cleaning operation scheduling scheme adapted to the actual operation scenario, which is then visualized and output. Simultaneously, the operation execution status is monitored in real time, and the scheduling scheme is dynamically updated. Using this invention, intelligent, precise, and dynamic scheduling of cleaning operations under multiple constraints can be achieved, significantly improving the scheduling efficiency and resource utilization of cleaning operations.

The invention discloses a natural gas pipeline network scheduling method, electronic equipment and a storage medium, relates to the technical field of natural gas pipeline scheduling, and aims to determine a better natural gas pipeline network scheduling scheme. The method comprises the following steps: obtaining a linearized mathematical model; solving the target function based on the flow constraint and the operation flow constraint of the compressor at the supercharging node to obtain an initial optimization result; according to the first search step size, based on the initial optimization result and a penalty sequence linear programming algorithm, solving the linearized mathematical model to obtain a first optimization result; according to a second search step length, based on the first optimization result and a penalty sequence linear programming algorithm, solving the linearized mathematical model to obtain a second optimization result; based on the third search step size, the second optimization result and a penalty sequence linear programming algorithm, solving the linearized mathematical model to obtain a third optimization result; and determining a natural gas pipeline network scheduling scheme based on the third optimization result.

The invention discloses an optimized operation method of an off-grid direct-current micro-grid. The off-grid direct-current micro-grid comprises a photovoltaic power generation system, a battery energy storage system, a fuel cell and an electrolytic cell which are connected through a direct-current bus. The optimized operation method comprises the following steps: constructing a system mathematical model of an off-grid direct current micro-grid, and defining a power balance relationship between a direct current load and each energy component; the system mathematical model comprises mathematical models of a photovoltaic power generation system, a battery energy storage system, a fuel cell, an electrolytic cell and a direct current load; based on the system mathematical model, establishing a linear optimization model by taking minimization of hydrogen fuel consumption or maximization of electrolytic cell hydrogen energy production as a target; the constraint condition of the linear optimization model comprises a power balance relation; and solving the linear optimization model by adopting a linear programming algorithm so as to dynamically distribute power output of each energy component, and controlling the operation of the micro-grid based on a solving result. The method can solve the problems that in the prior art, an off-grid direct-current micro-grid is high in operation cost, and an optimization algorithm is complex in calculation and difficult to apply in real time.

The invention relates to the technical field of effect value distribution, in particular to an effect value distribution method, system, equipment and medium based on data dual-attribute driving, and the method comprises the steps: collecting multi-source heterogeneous data in real time through a big data analysis tool, and carrying out the preprocessing to obtain a multi-source heterogeneous data set; carrying out key feature extraction by adopting a feature engineering technology to obtain a key feature set of the data; adopting a time sequence analysis technology to obtain dynamic effect characteristics; evaluating the importance of the dynamic effect features to obtain feature importance scores; the machine learning model generates a service decision result according to the relation between the dynamic effect features which are not subjected to feature importance scoring and the feature importance scores; and constructing a marketization distribution model by using a linear programming algorithm, and distributing the total income. According to the method, a data provider can be stimulated to actively provide high-quality data, sharing and circulation of the data are promoted, and trust and cooperation between a data user and the provider are enhanced.